Pith Number

pith:M3PBBCOO

pith:2025:M3PBBCOOUVRH3IOEZVIWJSJN2J

not attested not anchored not stored refs pending

Reinforcement Learning for Long-Horizon Interactive LLM Agents

Aleksei Petrenko, Brody Huval, Jackson Hamburger, Kevin Chen, Marco Cusumano-Towner, Philipp Kr\"ahenb\"uhl, Vladlen Koltun

arxiv:2502.01600 v3 · 2025-02-03 · cs.LG · cs.AI

Open paper page JSON Open Graph Bundle Merged state Verified badge What is a Pith Number?

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{M3PBBCOOUVRH3IOEZVIWJSJN2J}

Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge

Record completeness

1 Bitcoin timestamp

2 Internet Archive

3 Author claim open · sign in to claim

4 Citations open

5 Replications open

✓ Portable graph bundle live · download bundle · merged state

The bundle contains the canonical record plus signed events. A mirror can host it anywhere and recompute the same current state with the deterministic merge algorithm.

Cited by

36 papers in Pith

Diagnosing Task Insensitivity in Language Agents

Group-Graph Policy Optimization for Long-Horizon Agentic Reinforcement Learning

Shattering the Autoregressive Curse: Dynamic Epistemic Entropy Orchestrated Erasable Reinforcement Learning for LLMs

Rank-Then-Act: Reward-Free Control from Frame-Order Progress

WorldSample: Closed-loop Real-robot RL with World Modelling

Receipt and verification

First computed	2026-07-05T10:26:43.513663Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

66de1089cea5627da1c4cd5164c92dd25259d9d162f4b400319a9a0e65b66151

Aliases

arxiv: 2502.01600 · arxiv_version: 2502.01600v3 · doi: 10.48550/arxiv.2502.01600 · pith_short_12: M3PBBCOOUVRH · pith_short_16: M3PBBCOOUVRH3IOE · pith_short_8: M3PBBCOO

Agent API

Resolver JSON Graph JSON Events JSON Schema Signing key

Verify this Pith Number yourself

curl -sH 'Accept: application/ld+json' https://pith.science/pith/M3PBBCOOUVRH3IOEZVIWJSJN2J \
  | jq -c '.canonical_record' \
  | python3 -c "import sys,json,hashlib; b=json.dumps(json.loads(sys.stdin.read()), sort_keys=True, separators=(',',':'), ensure_ascii=False).encode(); print(hashlib.sha256(b).hexdigest())"
# expect: 66de1089cea5627da1c4cd5164c92dd25259d9d162f4b400319a9a0e65b66151

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "4cd7700f5ecf8cfba416fe85de5b8834e070056a886d5c04b88ecbcaf95ab900",
    "cross_cats_sorted": [
      "cs.AI"
    ],
    "license": "http://creativecommons.org/licenses/by-nc-nd/4.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2025-02-03T18:35:42Z",
    "title_canon_sha256": "4009082a2c598a4e641ebf2e0ea5d330c4aa6a99b1973b6d954a0ed70be87661"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2502.01600",
    "kind": "arxiv",
    "version": 3
  }
}